Machine learning improves early prediction of organ failure in hyperlipidemia acute pancreatitis using clinical and abdominal CT features.

BACKGROUND: This study aimed to investigate and validate machine-learning predictive models combining computed tomography and clinical data to early predict organ failure (OF) in Hyperlipidemic acute pancreatitis (HLAP). METHODS: Demographics, laboratory parameters and computed tomography imaging data of 314 patients with HLAP from the First Affiliated Hospital of Wenzhou Medical University between 2017 and 2021, were retrospectively analyzed. Sixty-five percent of patients (n = 204) were assigned to the training group and categorized as patients with and without OF. Parameters were compared by univariate analysis. Machine-learning methods including random forest (RF) were used to establish model to predict OF of HLAP. Areas under the curves (AUCs) of receiver operating characteristic were calculated. The remaining 35% patients (n = 110) were assigned to the validation group to evaluate the performance of models to predict OF. RESULTS: Ninety-three (45.59%) and fifty (45.45%) patients from the training and the validation cohort, respectively, developed OF. The RF model showed the best performance to predict OF, with the highest AUC value of 0.915. The sensitivity (0.828) and accuracy (0.814) of RF model were both the highest among the five models in the study cohort. In the validation cohort, RF model continued to show the highest AUC (0.820), accuracy (0.773) and sensitivity (0.800) to predict OF in HLAP, while the positive and negative likelihood ratios and post-test probability were 3.22, 0.267 and 72.85%, respectively. CONCLUSIONS: Machine-learning models can be used to predict OF occurrence in HLAP in our pilot study. RF model showed the best predictive performance, which may be a promising candidate for further clinical validation.

Novel anthropometric indicators of visceral obesity predict the severity of hyperlipidemic acute pancreatitis.

BACKGROUND: Obesity substantially contributes to the onset of acute pancreatitis (AP) and influences its progression to severe AP. Although body mass index (BMI) is a widely used anthropometric parameter, it fails to delineate the distribution pattern of adipose tissue. To circumvent this shortcoming, the predictive efficacies of novel anthropometric indicators of visceral obesity, such as lipid accumulation products (LAP), cardiometabolic index (CMI), body roundness index (BRI), visceral adiposity index (VAI), A Body Shape Index (ABSI), and Chinese visceral adiposity index (CVAI) were examined to assess the severity of AP. METHOD: The body parameters and laboratory indices of 283 patients with hyperlipidemic acute pancreatitis (HLAP) were retrospectively analysed, and the six novel anthropometric indicators of visceral obesity were calculated. The severity of HLAP was determined using the revised Atlanta classification. The correlation between the six indicators and HLAP severity was evaluated, and the predictive efficacy of the indicators was assessed using area under the curve (AUC). The differences in diagnostic values of the six indicators were also compared using the DeLong test. RESULTS: Patients with moderate to severe AP had higher VAI, CMI, and LAP than patients with mild AP (all P < 0.001). The highest AUC in predicting HLAP severity was observed for VAI, with a value of 0.733 and 95% confidence interval of 0.678-0.784. CONCLUSIONS: This study demonstrated significant correlations between HLAP severity and VAI, CMI, and LAP indicators. These indicators, particularly VAI, which displayed the highest predictive power, were instrumental in forecasting and evaluating the severity of HLAP.

Coronary artery-bronchial artery fistula imaging characteristics and its correlation with pulmonary disease severity.

Hemoptysis is a common clinical emergency, bronchial arterial embolization is considered to be an effective treatment. The presence of coronary artery-bronchial artery fistula (CBF) may lead to recurrence of hemoptysis after treatment. It is necessary to investigate the imaging characteristics of a CBF and its correlation with the severity of pulmonary disease. With the development of multi-detector computed tomography, our study used the 320-slice CT bronchial artery angiography technology to observe and visualize blood vessels. The image and clinical data of 2015 hemoptysis patients with 320-slice CT bronchial artery angiography were retrospectively reviewed from January 2015 to December 2019. The axial and three-dimensional CT images were analyzed. The incidence, anatomical characteristics of CBF and pulmonary disease severity score were evaluated. A total of 12 CBF vessels were detected in 11 patients. We found that the incidence of CBF in this group was 0.55% (11/2015). Mean CBF diameter was 1.9 mm (1.2-2.5 mm). The course of CBF usually was relatively fixed. The proportions of CBF originated from the left circumflex artery, right coronary artery, and left anterior descending artery were 75%, 16.7% and 8.3%, respectively. Preliminarily analysis of the correlation between the trend of CBF and the pulmonary diseases severity score showed that CBF was more likely to communicate with a bronchial artery on the side with a higher severity score. CBF may occur in patients with chronic pulmonary disease and hemoptysis, and its origin, course and trend are characteristic. Detailed and comprehensive computed tomography angiography image analysis is helpful to improve the clinical treatment of hemoptysis with CBF.

The Value of 320-Row Multidetector CT Bronchial Arteriography in Recurrent Hemoptysis after Failed Transcatheter Arterial Embolization.

PURPOSE: To retrospectively assess the value of computed tomographic (CT) bronchial arteriography (BA) with 320-row multidetector CT in the management of patients with recurrent hemoptysis immediately after bronchial artery embolization (BAE). MATERIALS AND METHODS: Among 135 consecutive patients treated with BAE between April 2014 and March 2016, recurrent hemoptysis developed in 15, and 10 subsequently underwent multidetector CT. Vascular abnormalities and associated anatomy were evaluated to determine the potential cause of BAE failure, and the clinical impacts of CT BA were analyzed. RESULTS: CT BA revealed an additional 22 abnormal vessels in the qualified 10 patients, and 8 patients were treated again within 24 hours after the first BAE based on multidetector CT findings. Of the 22 abnormal vessels, 16 were embolized, including 4 orthotopic arteries, 8 ectopic arteries, and 4 nonbronchial systemic arteries (NBSAs); the remaining 6 abnormal arteries were not embolized because of normal BA (n = 1), anatomic inaccessibility (n = 2), or cessation of hemoptysis with conservative therapy (n = 3). There were no further cases of recurrent hemoptysis after the second intervention, with a mean follow-up of 7.7 months ± 6.7. Overall, initial conventional BA missed 65% of potential bleeding arteries (22 of 34). After CT BA, 73% of the newly identified vessels (16 of 22) were embolized. CONCLUSIONS: Multiple unrecognized abnormal ectopic bronchial arteries and NBSAs are the major causes of failure of initial BAE. Multidetector CT BA can precisely identify a large number of feeding vessels that are missed on conventional BA, allowing for repeat embolization with a high success rate.

Radiomics Is Effective for Distinguishing Coronavirus Disease 2019 Pneumonia From Influenza Virus Pneumonia.

Objectives: To develop and validate a radiomics model for distinguishing coronavirus disease 2019 (COVID-19) pneumonia from influenza virus pneumonia. Materials and Methods: A radiomics model was developed on the basis of 56 patients with COVID-19 pneumonia and 90 patients with influenza virus pneumonia in this retrospective study. Radiomics features were extracted from CT images. The radiomics features were reduced by the Max-Relevance and Min-Redundancy algorithm and the least absolute shrinkage and selection operator method. The radiomics model was built using the multivariate backward stepwise logistic regression. A nomogram of the radiomics model was established, and the decision curve showed the clinical usefulness of the radiomics nomogram. Results: The radiomics features, consisting of nine selected features, were significantly different between COVID-19 pneumonia and influenza virus pneumonia in both training and validation data sets. The receiver operator characteristic curve of the radiomics model showed good discrimination in the training sample [area under the receiver operating characteristic curve (AUC), 0.909; 95% confidence interval (CI), 0.859-0.958] and in the validation sample (AUC, 0.911; 95% CI, 0.753-1.000). The nomogram was established and had good calibration. Decision curve analysis showed that the radiomics nomogram was clinically useful. Conclusions: The radiomics model has good performance for distinguishing COVID-19 pneumonia from influenza virus pneumonia and may aid in the diagnosis of COVID-19 pneumonia.

Dynamic changes on chest CT of COVID-19 patients with solitary pulmonary lesion in initial CT.

PURPOSE: To investigate the dynamic evolution of image features of COVID-19 patients appearing as a solitary lesion at initial chest CT scan. MATERIALS AND METHODS: Twenty-two COVID-19 patients with solitary pulmonary lesion from three hospitals in China were enrolled from January 18, 2020 to March 18, 2020. The clinical feature and laboratory findings at first visit, as well as characteristics and dynamic evolution of chest CT images were analyzed. Among them, the CT score evaluation was the sum of the lung involvement in five lobes (0-5 points for each lobe, with a total score ranging from 0 to 25). RESULTS: 22 COVID-19 patients (11 males and 11 females, with an average age of 40.7 ± 10.3) developed a solitary pulmonary lesion within 4 days after the onset of symptoms, the peak time of CT score was about 11 days (with a median CT score of 6), and was discharged about 19 days. The peak of CT score was positively correlated with the peak time and the discharge time (p < 0.001, r = 0.793; p < 0.001, r = 0.715). Scan-1 (first visit): 22 cases (100%) showed GGO and one lobe was involved, CT score was 1.0/1.0 (median/IQR). Scan-2 (peak): 15 cases (68%) showed crazy-paving pattern, 19 cases (86%) showed consolidation, and 2.5 lobes were involved, CT score was 6.0/12.0. Scan-3 (before discharge): ten cases (45%) showed linear opacities, none had crazy-paving pattern, and 2.5 lobes were involved, CT score was 6.0/11.0. Scan-4 (after discharge): three cases (19%) showed linear opacities and one lobe was involved, CT score was 2.0/5.0. CONCLUSION: The chest CT features are related to the course of COVID-19 disease, and dynamic chest CT scan are helpful to monitor disease progress and patients' condition. In recovered patients with COVID-19, the positive CT manifestations were found within 4 days, lung involvement peaking at approximately 11 days, and discharged at about 19 days. The patients with more severe the lung injury was, the later the peak time appeared and the longer the recovery time was. Although the lesion was resolved over time, isolation and reexamination were required after discharge.

Whole-brain CT perfusion imaging using increased sampling intervals: A pilot study.

The aim of the present study was to investigate the feasibility of whole-brain perfusion imaging using the increased sampling interval protocol for 320-detector row dynamic-volume computed tomography (CT). A total of 12 volunteers were recruited. The novel protocols with 11 volumes (defined as protocol P11) and 15 volumes (defined as protocol P15) were performed on the volunteers to evaluate whether P11 and P15 are able to acquire comparable results to the standard protocol with 19 volumes (defined as protocol P19) according to the as-low-as-reasonably-achievable principle. All data were acquired using a dynamic-volume CT scanner with a 16 cm-wide detector with 320 rows. The scanned transverse images from volunteers were analyzed using the Volume-Engineered System workstation. The MedCalc software package was used for Bland-Altman analysis of all variables. The data inconsistency of mean transit time (MTT), cerebral blood volume (CBV), cerebral blood flow (CBF), and time to peak (TTP) between P11/P15 and P19 were all <5%, and the data were trustworthy. The mean differences of MTT, CBV, CBF and TTP between P15 and P19 were less than those between P11 and P19. The consistencies of perfusion parameters acquired with protocols P15 and P19 were higher compared with those acquired with P11. In whole-brain perfusion, the new protocol P15 has higher consistency with P19 than P11, and the radiation dose may be reduced by ~16% without degradation of perfusion parameters. Therefore, P15 should be recommended as a routine procedure in whole-brain perfusion imaging.

Metabolite changes in the ipsilateral and contralateral cerebral hemispheres in rats with middle cerebral artery occlusion.

Cerebral ischemia not only causes pathological changes in the ischemic areas but also induces a series of secondary changes in more distal brain regions (such as the contralateral cerebral hemisphere). The impact of supratentorial lesions, which are the most common type of lesion, on the contralateral cerebellum has been studied in patients by positron emission tomography, single photon emission computed tomography, magnetic resonance imaging and diffusion tensor imaging. In the present study, we investigated metabolite changes in the contralateral cerebral hemisphere after supratentorial unilateral ischemia using nuclear magnetic resonance spectroscopy-based metabonomics. The permanent middle cerebral artery occlusion model of ischemic stroke was established in rats. Rats were randomly divided into the middle cerebral artery occlusion 1-, 3-, 9- and 24-hour groups and the sham group. 1H nuclear magnetic resonance spectroscopy was used to detect metabolites in the left and right cerebral hemispheres. Compared with the sham group, the concentrations of lactate, alanine, γ-aminobutyric acid, choline and glycine in the ischemic cerebral hemisphere were increased in the acute stage, while the concentrations of N-acetyl aspartate, creatinine, glutamate and aspartate were decreased. This demonstrates that there is an upregulation of anaerobic glycolysis (shown by the increase in lactate), a perturbation of choline metabolism (suggested by the increase in choline), neuronal cell damage (shown by the decrease in N-acetyl aspartate) and neurotransmitter imbalance (evidenced by the increase in γ-aminobutyric acid and glycine and by the decrease in glutamate and aspartate) in the acute stage of cerebral ischemia. In the contralateral hemisphere, the concentrations of lactate, alanine, glycine, choline and aspartate were increased, while the concentrations of γ-aminobutyric acid, glutamate and creatinine were decreased. This suggests that there is a difference in the metabolite changes induced by ischemic injury in the contralateral and ipsilateral cerebral hemispheres. Our findings demonstrate the presence of characteristic changes in metabolites in the contralateral hemisphere and suggest that they are most likely caused by metabolic changes in the ischemic hemisphere.